© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69974
    Prev
    Next
    INDEX
    Explanations

    asking or considering questions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on punctuation marks that signal sentence or clause boundaries (e.g. periods, question marks, commas).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fhould
    -1.09
    leté
    -1.08
     ạ
    -1.06
     devraient
    -1.02
    紆
    -1.01
     कृपया
    -1.00
     سایر
    -0.99
    ↄ
    -0.99
    }?>
    -0.98
    tomatik
    -0.98
    POSITIVE LOGITS
     Are
    3.03
     are
    2.95
    Are
    2.63
     is
    2.39
     Is
    2.20
     Does
    2.11
     what
    2.05
    Is
    1.97
     does
    1.95
     if
    1.91
    Activations Density 0.026%

    No Known Activations